Supercharge your AI agents with data from the web and beyond. Building the library for superintelligence. 🔥
TypeScript aiai-agentsai-crawlerai-scrapingai-searchcrawlerdata-extractionhtml-to-markdownllmmarkdownscraperscrapingweb-crawlerweb-dataweb-data-extractionweb-scraperweb-scrapingweb-searchwebscraping
feat-sdk/cancel-crawl
rafaelsideguide2689ffa74878
diff --git a/apps/js-sdk/firecrawl/src/index.ts b/apps/js-sdk/firecrawl/src/index.tsindex a62150373..8b60cf862 100644--- a/apps/js-sdk/firecrawl/src/index.ts+++ b/apps/js-sdk/firecrawl/src/index.ts@@ -421,6 +421,36 @@ export default class FirecrawlApp {return { success: false, error: "Internal server error." };}+ /**+ * Cancels a crawl job using the Firecrawl API.+ * @param id - The ID of the crawl operation.+ * @returns The response from the cancel crawl operation.+ */+ async cancelCrawl(id: string): Promise<ErrorResponse> {+ const headers = this.prepareHeaders();+ try {+ const response: AxiosResponse = await this.deleteRequest(+ `${this.apiUrl}/v1/crawl/${id}`,+ headers+ );+ if (response.status === 200) {+ return response.data;+ } else {+ this.handleError(response, "cancel crawl job");+ }+ } catch (error: any) {+ throw new FirecrawlError(error.message, 500);+ }+ return { success: false, error: "Internal server error." };+ }++ /**+ * Initiates a crawl job and returns a CrawlWatcher to monitor the job via WebSocket.+ * @param url - The URL to crawl.+ * @param params - Additional parameters for the crawl request.+ * @param idempotencyKey - Optional idempotency key for the request.+ * @returns A CrawlWatcher instance to monitor the crawl job.+ */async crawlUrlAndWatch(url: string,params?: CrawlParams,@@ -436,6 +466,12 @@ export default class FirecrawlApp {throw new FirecrawlError("Crawl job failed to start", 400);}+ /**+ * Maps a URL using the Firecrawl API.+ * @param url - The URL to map.+ * @param params - Additional parameters for the map request.+ * @returns The response from the map operation.+ */async mapUrl(url: string, params?: MapParams): Promise<MapResponse | ErrorResponse> {const headers = this.prepareHeaders();let jsonData: { url: string } & MapParams = { url, ...params };@@ -506,6 +542,27 @@ export default class FirecrawlApp {}}+ /**+ * Sends a DELETE request to the specified URL.+ * @param url - The URL to send the request to.+ * @param headers - The headers for the request.+ * @returns The response from the DELETE request.+ */+ async deleteRequest(+ url: string,+ headers: AxiosRequestHeaders+ ): Promise<AxiosResponse> {+ try {+ return await axios.delete(url, { headers });+ } catch (error) {+ if (error instanceof AxiosError && error.response) {+ return error.response as AxiosResponse;+ } else {+ throw error;+ }+ }+ }+/*** Monitors the status of a crawl job until completion or failure.* @param id - The ID of the crawl operation.diff --git a/apps/python-sdk/firecrawl/firecrawl.py b/apps/python-sdk/firecrawl/firecrawl.pyindex 97f4e04f8..f153b034d 100644--- a/apps/python-sdk/firecrawl/firecrawl.py+++ b/apps/python-sdk/firecrawl/firecrawl.py@@ -191,6 +191,23 @@ class FirecrawlApp:}else:self._handle_error(response, 'check crawl status')++ def cancel_crawl(self, id: str) -> Dict[str, Any]:+ """+ Cancel an asynchronous crawl job using the Firecrawl API.++ Args:+ id (str): The ID of the crawl job to cancel.++ Returns:+ Dict[str, Any]: The response from the cancel crawl request.+ """+ headers = self._prepare_headers()+ response = self._delete_request(f'{self.api_url}/v1/crawl/{id}', headers)+ if response.status_code == 200:+ return response.json()+ else:+ self._handle_error(response, "cancel crawl job")def crawl_url_and_watch(self, url: str, params: Optional[Dict[str, Any]] = None, idempotency_key: Optional[str] = None) -> 'CrawlWatcher':"""@@ -321,6 +338,33 @@ class FirecrawlApp:else:return responsereturn response++ def _delete_request(self, url: str,+ headers: Dict[str, str],+ retries: int = 3,+ backoff_factor: float = 0.5) -> requests.Response:+ """+ Make a DELETE request with retries.++ Args:+ url (str): The URL to send the DELETE request to.+ headers (Dict[str, str]): The headers to include in the DELETE request.+ retries (int): Number of retries for the request.+ backoff_factor (float): Backoff factor for retries.++ Returns:+ requests.Response: The response from the DELETE request.++ Raises:+ requests.RequestException: If the request fails after the specified retries.+ """+ for attempt in range(retries):+ response = requests.delete(url, headers=headers)+ if response.status_code == 502:+ time.sleep(backoff_factor * (2 ** attempt))+ else:+ return response+ return responsedef _monitor_job_status(self, id: str, headers: Dict[str, str], poll_interval: int) -> Any:"""